Melanoma is a fatal type of skin cancer; the fury spread results in a high fatality rate when the malignancy is not treated at an initial stage. The patients’ lives can be saved by accurately detecting skin cancer at an initial stage. A quick and precise diagnosis might help increase the patient’s survival rate. It necessitates the development of a computer-assisted diagnostic support system. This research proposes a novel deep transfer learning model for melanoma classification using MobileNetV2. The MobileNetV2 is a deep convolutional neural network that classifies the sample skin lesions as malignant or benign. The performance of the proposed deep learning model is evaluated using the ISIC 2020 dataset. The dataset contains less than 2% malignant samples, raising the class imbalance. Various data augmentation techniques were applied to tackle the class imbalance issue and add diversity to the dataset. The experimental results demonstrate that the proposed deep learning technique outperforms state-of-the-art deep learning techniques in terms of accuracy and computational cost.

The increasing global population at a rapid pace makes road traffic dense; managing such massive traffic is challenging. In developing countries like Pakistan, road traffic accidents (RTA) have the highest mortality percentage among other Asian countries. The main reasons for RTAs are road cracks and potholes. Understanding the need for an automated system for the detection of cracks and potholes, this study proposes a decision support system (DSS) for an autonomous road information system for smart city development with the use of deep learning. The proposed DSS works in layers where initially the image of roads is captured and coordinates attached to the image with the help of global positioning system (GPS), communicated to the decision layer to find about the cracks and potholes in the roads, and eventually, that information is passed to the road management information system, which gives information to drivers and the maintenance department. For the decision layer, we projected a CNN-based model for pothole crack detection (PCD). Aimed at training, a K-fold cross-validation strategy was used where the value of K was set to 10. The training of PCD was completed with a self-collected dataset consisting of 6000 images from Pakistani roads. The proposed PCD achieved 98% of precision, 97% recall, and accuracy while testing on unseen images. The results produced by our model are higher than the existing model in terms of performance and computational cost, which proves its significance.

Knowledge Graphs (KGs) are becoming essential to information systems that require access to structured data. Several approaches have been recently proposed, for obtaining vector representations of KGs suitable for Machine Learning tasks, based on identifying and extracting relevant graph substructures using uniform and biased random walks. However, such approaches lead to representations comprising mostly "popular", instead of "relevant", entities in the KG. In KGs, in which different types of entities often exist (such as in Linked Open Data), a given target entity may have its own distinct set of most "relevant" nodes and edges. We propose specificity as an accurate measure of identifying most relevant, entity-specific, nodes and edges. We develop a scalable method based on bidirectional random walks to compute specificity. Our experimental evaluation results show that specificity-based biased random walks extract more "meaningful" (in terms of size and relevance) RDF substructures compared to the state-of-the-art and, the graph embedding learned from the extracted substructures, outperform existing techniques in the task of entity recommendation in DBpedia.

No abstract

No abstract